Copertina

Local Intrinsic Dimension of Representations Predicts Alignment and Generalization in AI Models and Human Brain

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yu, Junjie, Ma, Wenxiao, Wei, Chen, Zhang, Jianyu, Deng, Haotian, Deng, Zihan, Liu, Quanying
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Understanding Generalization from Embedding Dimension and Distributional Convergence
di: Yu, Junjie, et al.
Pubblicazione: (2026)

Scale-Invariance Drives Convergence in AI and Brain Representations
di: Yu, Junjie, et al.
Pubblicazione: (2025)

Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation
di: Yu, Junjie, et al.
Pubblicazione: (2026)

Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering Human Perceptual Variability on Facial Expressions
di: Deng, Haotian, et al.
Pubblicazione: (2025)

DCHO: A Decomposition-Composition Framework for Predicting Higher-Order Brain Connectivity to Enhance Diverse Downstream Applications
di: Li, Weibin, et al.
Pubblicazione: (2025)

Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability
di: Wei, Chen, et al.
Pubblicazione: (2025)

Measuring the Intrinsic Dimension of Earth Representations
di: Rao, Arjun, et al.
Pubblicazione: (2025)

Rethinking Intrinsic Dimension Estimation in Neural Representations
di: Schulte, Rickmer, et al.
Pubblicazione: (2026)

Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning
di: Qian, Fuyuan, et al.
Pubblicazione: (2026)

A Combination Model Based on Sequential General Variational Mode Decomposition Method for Time Series Prediction
di: Chen, Wei, et al.
Pubblicazione: (2024)

Salutary Labeling with Zero Human Annotation
di: Xiao, Wenxiao, et al.
Pubblicazione: (2024)

CoCoG: Controllable Visual Stimuli Generation based on Human Concept Representations
di: Wei, Chen, et al.
Pubblicazione: (2024)

Less is More: Local Intrinsic Dimensions of Contextual Language Models
di: Ruppik, Benjamin Matthias, et al.
Pubblicazione: (2025)

GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models
di: Zhang, Zhanwei, et al.
Pubblicazione: (2025)

Rubric-Conditioned LLM Grading: Alignment, Uncertainty, and Robustness
di: Deng, Haotian, et al.
Pubblicazione: (2025)

BrainFLORA: Uncovering Brain Concept Representation via Multimodal Neural Embeddings
di: Li, Dongyang, et al.
Pubblicazione: (2025)

Dimensions of Vulnerability in Visual Working Memory: An AI-Driven Approach to Perceptual Comparison
di: Cao, Yuang, et al.
Pubblicazione: (2025)

Separating Intrinsic Ambiguity from Estimation Uncertainty in Deep Generative Models for Linear Inverse Problems
di: Guo, Yuxin, et al.
Pubblicazione: (2026)

A Connection Between Score Matching and Local Intrinsic Dimension
di: Yeats, Eric, et al.
Pubblicazione: (2025)

Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation
di: Osada, Genki
Pubblicazione: (2026)

eDCF: Estimating Intrinsic Dimension using Local Connectivity
di: Gupta, Dhruv, et al.
Pubblicazione: (2025)

Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts
di: Tulchinskii, Eduard, et al.
Pubblicazione: (2023)

G2LTraj: A Global-to-Local Generation Approach for Trajectory Prediction
di: Zhang, Zhanwei, et al.
Pubblicazione: (2024)

Teaching CORnet Human fMRI Representations for Enhanced Model-Brain Alignment
di: Lu, Zitong, et al.
Pubblicazione: (2024)

On Convolutions, Intrinsic Dimension, and Diffusion Models
di: Leung, Kin Kwan, et al.
Pubblicazione: (2025)

Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment
di: Shao, Yawen, et al.
Pubblicazione: (2025)

A Wiener Process Perspective on Local Intrinsic Dimension Estimation Methods
di: Tempczyk, Piotr, et al.
Pubblicazione: (2024)

Contrastive Learning of Shared Spatiotemporal EEG Representations Across Individuals for Naturalistic Neuroscience
di: Shen, Xinke, et al.
Pubblicazione: (2024)

Optimal Stochastic Trace Estimation in Generative Modeling
di: Liu, Xinyang, et al.
Pubblicazione: (2025)

Conformal Tail Risk Control for Large Language Model Alignment
di: Chen, Catherine Yu-Chi, et al.
Pubblicazione: (2025)

Memory Sequence Length of Data Sampling Impacts the Adaptation of Meta-Reinforcement Learning Agents
di: Zhang, Menglong, et al.
Pubblicazione: (2024)

A Combination Model for Time Series Prediction using LSTM via Extracting Dynamic Features Based on Spatial Smoothing and Sequential General Variational Mode Decomposition
di: Liu, Jianyu, et al.
Pubblicazione: (2024)

A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models
di: Kamkari, Hamidreza, et al.
Pubblicazione: (2024)

On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension
di: Chakraborty, Saptarshi, et al.
Pubblicazione: (2024)

Achieving More Human Brain-Like Vision via Human EEG Representational Alignment
di: Lu, Zitong, et al.
Pubblicazione: (2024)

Predicting Human Brain States with Transformer
di: Sun, Yifei, et al.
Pubblicazione: (2024)

AI for the Open-World: the Learning Principles
di: Zhang, Jianyu
Pubblicazione: (2025)

Aggregation Alignment for Federated Learning with Mixture-of-Experts under Data Heterogeneity
di: Fang, Zihan, et al.
Pubblicazione: (2026)

Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models
di: Yang, Junjie, et al.
Pubblicazione: (2025)

On the Intrinsic Dimensions of Data in Kernel Learning
di: Takhanov, Rustem
Pubblicazione: (2026)